增量学习
_Blueblue_
ok fine
展开
-
【元学习】MER代码实现:Task/Class-IL增量场景下的Meta-Experience Replay详解
论文《Learning to learn without forgetting by maximizing transfer and minimizing interference》中提出了“将经验重放与元学习相结合“的增量学习方法:Meta-Experience Replay (MER)。这里整理了一下MER的算法流程和代码实现。论文解析可以戳这里:论文解析:Learning to learn without forgetting by maximizing transfer and mi原创 2021-09-26 19:29:47 · 2017 阅读 · 1 评论 -
【元学习】iTAML论文精读:持续/增量学习下与任务无关的元学习模型
论文:J. Rajasegaran, S. Khan, M. Hayat, F. S. Khan, M. Shah, itaml: An incremental task-agnostic meta-learning approach, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 13588–13597.在CVPR2020上发表的一篇结合元学习和增量学习的原创 2021-09-14 14:20:00 · 923 阅读 · 4 评论 -
【元学习】MER论文解析:持续/增量学习下的元学习模型
论文:M. Reimer, I. Cases, R. Ajemian, M. Liu, I. Rish, Y. Tu, G. Tesauro, Learning to learn without forgetting by maximizing transfer and minimizing interference, in: ICLR, 2019.提出了Meta-Experience Replay (MER) 模型,将经验重放与基于优化的元学习相结合,基于Reptile元学习模型,以最大限度地转移和.原创 2021-08-31 17:21:13 · 1213 阅读 · 0 评论 -
【增量学习】综述解析:A continual learning survey: Defying forgetting in classification tasks
论文:Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., Tuytelaars, T., 2021. A continual learning survey: Defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence 1–1.原创 2021-08-30 15:37:05 · 1390 阅读 · 0 评论 -
【增量学习】综述解析:Online Continual Learning in Image Classification: An Empirical Survey
论文:Mai Z , Li R , Jeong J , et al. Online Continual Learning in Image Classification: An Empirical Survey[J]. arXiv, 2021.论文解析(内含论文原文、代码链接):https://ripe-heliotrope-6f4.notion.site/Online-Continual-Learning-in-Image-Classification-An-Empirical-Survey-25bb原创 2021-08-30 15:21:37 · 909 阅读 · 0 评论 -
【增量学习】Life Long Learning 《李宏毅2021持续/终身学习视频》讲解笔记
原视频网址:https://www.bilibili.com/video/BV1Wv411h7kN?p=84视频学习笔记:https://ripe-heliotrope-6f4.notion.site/Lifelong-Learning-05047c41964c4eacbab023823f1f6bef原创 2021-08-30 15:06:43 · 778 阅读 · 0 评论